{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:OQJ7MIPYLUQEA3RMRW4UNSKJBP","short_pith_number":"pith:OQJ7MIPY","canonical_record":{"source":{"id":"2607.28341","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-30T15:07:00Z","cross_cats_sorted":[],"title_canon_sha256":"f6e2ca516eb87a551e9768f20e73cf8bb04b67f4ae1223772f35eecdb955c032","abstract_canon_sha256":"637c763679cc1590c7ccff8af5dbabb30998931ba2fd19faa4f16372ae83dc33"},"schema_version":"1.0"},"canonical_sha256":"7413f621f85d20406e2c8db946c9490bcd32a698e9fca0c951e4457dd5b1bc3a","source":{"kind":"arxiv","id":"2607.28341","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.28341","created_at":"2026-07-31T01:37:20Z"},{"alias_kind":"arxiv_version","alias_value":"2607.28341v1","created_at":"2026-07-31T01:37:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28341","created_at":"2026-07-31T01:37:20Z"},{"alias_kind":"pith_short_12","alias_value":"OQJ7MIPYLUQE","created_at":"2026-07-31T01:37:20Z"},{"alias_kind":"pith_short_16","alias_value":"OQJ7MIPYLUQEA3RM","created_at":"2026-07-31T01:37:20Z"},{"alias_kind":"pith_short_8","alias_value":"OQJ7MIPY","created_at":"2026-07-31T01:37:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:OQJ7MIPYLUQEA3RMRW4UNSKJBP","target":"record","payload":{"canonical_record":{"source":{"id":"2607.28341","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-30T15:07:00Z","cross_cats_sorted":[],"title_canon_sha256":"f6e2ca516eb87a551e9768f20e73cf8bb04b67f4ae1223772f35eecdb955c032","abstract_canon_sha256":"637c763679cc1590c7ccff8af5dbabb30998931ba2fd19faa4f16372ae83dc33"},"schema_version":"1.0"},"canonical_sha256":"7413f621f85d20406e2c8db946c9490bcd32a698e9fca0c951e4457dd5b1bc3a","receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7413f621f85d20406e2c8db946c9490bcd32a698e9fca0c951e4457dd5b1bc3a","last_reissued_at":"2026-07-31T01:37:20.275473Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T01:37:20.275473Z"},"source_kind":"arxiv","source_id":"2607.28341","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-31T01:37:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bc2oxqO1y7roiiy0cNL7KfjYouLKalwfJgOHq3H22kj/fB+VIgsYaWKCQpYO5SQbe58tW6arm0vxrE2wf/0pBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:05:09.403046Z"},"content_sha256":"5cb06bedc201b826f7b7261a1bb4bfdf78a05b364be72d98f61f911e41ad3c16","schema_version":"1.0","event_id":"sha256:5cb06bedc201b826f7b7261a1bb4bfdf78a05b364be72d98f61f911e41ad3c16"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:OQJ7MIPYLUQEA3RMRW4UNSKJBP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Capturing Token Tendencies for Training-Free Token Pruning in Multimodal Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiayi Ji, Jie Gao, Jie Ma, Qian Chen, Rongrong Ji, Xiaoshuai Sun, Zhike Qiu","submitted_at":"2026-07-30T15:07:00Z","abstract_excerpt":"While visual token pruning is essential for efficient Multimodal Large Language Models (MLLMs), existing training-free methods suffer from a critical limitation: they rely on static, instantaneous heuristics to perform irreversible filtering. This approach ignores the hierarchical nature of MLLMs, where token importance often evolves dynamically rather than remaining fixed across layers. Consequently, tokens essential for deep-layer reasoning are often prematurely discarded by shallow-layer estimates. To address this, we propose Trend-aware Pruning, a novel framework that elevates pruning from"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28341","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.28341/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-31T01:37:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xFtCcropOKktLf63Vr4KpC1inl/QSZeXoWZpOw8sD7CR8nUi4jzKguRrWWPqADNZkqE5tFRRImWCKh2/j2DtCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:05:09.403849Z"},"content_sha256":"b1672ad9de8fd18396d8db3d4dc8e023c45290ed82f0ec0f85e70f0bbc8651f8","schema_version":"1.0","event_id":"sha256:b1672ad9de8fd18396d8db3d4dc8e023c45290ed82f0ec0f85e70f0bbc8651f8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OQJ7MIPYLUQEA3RMRW4UNSKJBP/bundle.json","state_url":"https://pith.science/pith/OQJ7MIPYLUQEA3RMRW4UNSKJBP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OQJ7MIPYLUQEA3RMRW4UNSKJBP/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T19:05:09Z","links":{"resolver":"https://pith.science/pith/OQJ7MIPYLUQEA3RMRW4UNSKJBP","bundle":"https://pith.science/pith/OQJ7MIPYLUQEA3RMRW4UNSKJBP/bundle.json","state":"https://pith.science/pith/OQJ7MIPYLUQEA3RMRW4UNSKJBP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OQJ7MIPYLUQEA3RMRW4UNSKJBP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OQJ7MIPYLUQEA3RMRW4UNSKJBP","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"637c763679cc1590c7ccff8af5dbabb30998931ba2fd19faa4f16372ae83dc33","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-30T15:07:00Z","title_canon_sha256":"f6e2ca516eb87a551e9768f20e73cf8bb04b67f4ae1223772f35eecdb955c032"},"schema_version":"1.0","source":{"id":"2607.28341","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.28341","created_at":"2026-07-31T01:37:20Z"},{"alias_kind":"arxiv_version","alias_value":"2607.28341v1","created_at":"2026-07-31T01:37:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28341","created_at":"2026-07-31T01:37:20Z"},{"alias_kind":"pith_short_12","alias_value":"OQJ7MIPYLUQE","created_at":"2026-07-31T01:37:20Z"},{"alias_kind":"pith_short_16","alias_value":"OQJ7MIPYLUQEA3RM","created_at":"2026-07-31T01:37:20Z"},{"alias_kind":"pith_short_8","alias_value":"OQJ7MIPY","created_at":"2026-07-31T01:37:20Z"}],"graph_snapshots":[{"event_id":"sha256:b1672ad9de8fd18396d8db3d4dc8e023c45290ed82f0ec0f85e70f0bbc8651f8","target":"graph","created_at":"2026-07-31T01:37:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2607.28341/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While visual token pruning is essential for efficient Multimodal Large Language Models (MLLMs), existing training-free methods suffer from a critical limitation: they rely on static, instantaneous heuristics to perform irreversible filtering. This approach ignores the hierarchical nature of MLLMs, where token importance often evolves dynamically rather than remaining fixed across layers. Consequently, tokens essential for deep-layer reasoning are often prematurely discarded by shallow-layer estimates. To address this, we propose Trend-aware Pruning, a novel framework that elevates pruning from","authors_text":"Jiayi Ji, Jie Gao, Jie Ma, Qian Chen, Rongrong Ji, Xiaoshuai Sun, Zhike Qiu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-30T15:07:00Z","title":"Capturing Token Tendencies for Training-Free Token Pruning in Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28341","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5cb06bedc201b826f7b7261a1bb4bfdf78a05b364be72d98f61f911e41ad3c16","target":"record","created_at":"2026-07-31T01:37:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"637c763679cc1590c7ccff8af5dbabb30998931ba2fd19faa4f16372ae83dc33","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-30T15:07:00Z","title_canon_sha256":"f6e2ca516eb87a551e9768f20e73cf8bb04b67f4ae1223772f35eecdb955c032"},"schema_version":"1.0","source":{"id":"2607.28341","kind":"arxiv","version":1}},"canonical_sha256":"7413f621f85d20406e2c8db946c9490bcd32a698e9fca0c951e4457dd5b1bc3a","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7413f621f85d20406e2c8db946c9490bcd32a698e9fca0c951e4457dd5b1bc3a","first_computed_at":"2026-07-31T01:37:20.275473Z","kind":"pith_receipt","last_reissued_at":"2026-07-31T01:37:20.275473Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.28341","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5cb06bedc201b826f7b7261a1bb4bfdf78a05b364be72d98f61f911e41ad3c16","sha256:b1672ad9de8fd18396d8db3d4dc8e023c45290ed82f0ec0f85e70f0bbc8651f8"],"state_sha256":"a199bb5dd4b0e7ee68e5a35dfd56aa8410b3cd9b649a0553cf9b97de798306cb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MDyiF8kZERBzovZ56WB+d2T+VwHVH5tVmUYE1/jQAiBwqmZG3keZ26EweEtLNoThQbGejpr6ie2g+My7uaKPAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T19:05:09.410119Z","bundle_sha256":"88b6d746e433ab8d58eafe786b632492afbe07fb9010085a77a96206151bd933"}}